一作ICLR 2026Poster· Reinforcement Learning / Deep RL
Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
Trung Hieu Nguyen · Bao Nguyen · Wenao Ma · Yuzhi Zhao · Ruifeng She · Viet Anh Nguyen
强化学习与后训练OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Trung Hieu Nguyen · Bao Nguyen · Wenao Ma · Yuzhi Zhao · Ruifeng She · Viet Anh Nguyen